Extreme semi-supervised learning for multiclass classification

Chen, Chuangquan; Gan, Yanfen; Vong, Chi‐Man

doi:10.1016/j.neucom.2019.09.039

Cited by 10 publications

(10 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, support is required to get the best-generated samples for the discriminator. So, the authors are motivated by some techniques 7,8,[10][11][12] in generating realistic data with multi-class attributes. These techniques 7,8,[10][11][12] can generate real data by considering only a particular set of features and hence fail to result in the equal distribution of the given dataset.…”

Section: Motivationmentioning

confidence: 99%

“…So, the authors are motivated by some techniques 7,8,[10][11][12] in generating realistic data with multi-class attributes. These techniques 7,8,[10][11][12] can generate real data by considering only a particular set of features and hence fail to result in the equal distribution of the given dataset. Thus, the research gaps associated with existing GAN models are as follows:…”

Section: Motivationmentioning

confidence: 99%

“…2. Chen et al 11 proposed multi-GAN that trains a generator and a discriminator using a conditional information approach to assign class labels to dependent variables of the dataset. It calculates an auxiliary loss between the discriminator and the generator at training time.…”

Section: Motivationmentioning

confidence: 99%

See 2 more Smart Citations

GAN‐C: A generative adversarial network with a classifier for effective event prediction

Rajita

Halani

Shah

et al. 2022

Computational Intelligence

View full text Add to dashboard Cite

Event prediction is essential in social network (SN) analysis to study the SN's evolutionary patterns (communities). Machine learning (ML) models are often used to predict events in SN communities. The ML algorithms manifest the results with biasness for the same dataset. Hence, the performance of an ML model requires validation for the unseen data to avoid biasness in learning. Generally, researchers use the generative adversarial network (GAN) model for generating realistic sample data to enhance the prediction of events. It is challenging for the discriminator to learn features using a single layer with similar weights in a conventional GAN technique. Therefore, this article proposes an improved version of the GAN model named generative adversarial network classifier (GAN‐C). The proposed GAN‐C model contains an additional layer, called classifier, that generates different feature maps. Wherein weights are adjusted dynamically based on the conditions to predict the events. To be precise, conditioning the weights in a classifier layer using entropy values of the features is a simple and effective way to minimize the classifier loss function (categorical cross‐entropy). GAN‐C model results in 16% loss up to 10 batches, and after that, the loss becomes negligible and can generate non‐overlapping events. The gaps between such non‐overlapping events are analyzed using the Jensen–Shannon divergence technique. The experimental results show that the existing single‐GAN and multi‐GAN methods predict events with 79.34% and 82.17% accuracy, respectively. While the proposed GAN‐C comparatively predicts events with improved accuracy of 88.56% on the same dataset. The data generated by the GAN‐C model are also approximately 55.85% and 80.59% more realistic than multi‐GAN and single‐GAN, respectively, based on root mean square error and inception score comparisons. GAN‐C is also approximately 68.01% faster than other GAN models. Thus, this article's theoretical and experimental analysis justifies that GAN‐C works suitably for predicting events in a massive dataset.

show abstract

Section: Motivationmentioning

confidence: 99%

Section: Motivationmentioning

confidence: 99%

See 1 more Smart Citation

GAN‐C: A generative adversarial network with a classifier for effective event prediction

Rajita

Halani

Shah

et al. 2022

Computational Intelligence

View full text Add to dashboard Cite

show abstract

“…Examples include ELMs for online sequential learning [3], ELMs for imbalanced problems [4], ELMs for semi-supervised learning [5], ELMs for unsupervised learning [6], ELMs for compressive learning [8], etc. However, as analyzed in [9] [10], most of them still suffer from heavy overfitting and large model sizes for benchmark applications. This would restrict the broader applicability of ELMs, especially to computationally constrained devices such as mobile devices and wearables.…”

Section: Introductionmentioning

confidence: 99%

An Inverse-Free and Scalable Sparse Bayesian Extreme Learning Machine for Classification Problems

et al. 2021

Self Cite

View full text Add to dashboard Cite

Sparse Bayesian Extreme Learning Machine (SBELM) constructs an extremely sparse and probabilistic model with low computational cost and high generalization. However, the update rule of hyperparameters(ARD prior) in SBELM involves using the diagonal elements from the inversion of the covariance matrix with the full training dataset, which raises the following two issues. Firstly, inverting the Hessian matrix may suffer ill-conditioning issues in some cases, which hinders SBELM from converging. Secondly, it may result in the memory-overflow issue with computational memory ( 3 ) (L: number of hidden nodes) to invert the big covariance matrix for updating the ARD priors. To address these issues, an inverse-free SBELM called QN-SBELM is proposed in this paper, which integrates the gradient-based Quasi-Newton (QN) method into SBELM to approximate the inverse covariance matrix. It takes( 2 ) computational complexity and is simultaneously scalable to large problems. QN-SBELM was evaluated on benchmark datasets of different sizes. Experimental results verify that QN-SBELM achieves more accurate results than SBELM with a sparser model, and also provides more stable solutions and a great extension to large-scale problems.

show abstract

“…Thus, ELM is much faster and easier to implement than most state-of-the-art machine learning approaches. In the past decade, ELM theory and applications have attracted numerous attention, its variants and extensions have been developed for specific problems, such as online sequential learning [9], imbalance learning [10], multilabel learning [11], compressive learning [12], and compact modeling [13], etc. ELM was recently extended to hierarchical structure for dealing with complex tasks, i.e., multilayer ELM (ML-ELM).…”

Section: Introductionmentioning

confidence: 99%

Non-iterative and Fast Deep Learning: Multilayer Extreme Learning Machines

Zhang

Xiao

et al. 2020

Journal of the Franklin Institute

158

View full text Add to dashboard Cite

In the past decade, deep learning techniques have powered many aspects of our daily life, and drawn ever-increasing research interests. However, conventional deep learning approaches, such as deep belief network (DBN), restricted Boltzmann machine (RBM), and convolutional neural network (CNN), suffer from time-consuming training process due to fine-tuning of a large number of parameters and the complicated hierarchical structure. Furthermore, the above complication makes it difficult to theoretically analyze and prove the universal approximation of those conventional deep learning approaches. In order to tackle the issues, multilayer extreme learning machines (ML-ELM) were proposed, which accelerate the development of deep learning. Compared with conventional deep learning, ML-ELMs are non-iterative and fast due to the random feature mapping mechanism. In this paper, we perform a thorough review on the development of ML-ELMs, including stacked ELM autoencoder (ELM-AE), residual ELM, and local receptive field based ELM (ELM-LRF), as well as address their applications. In addition, we also discuss the connection between random neural networks and conventional deep learning.

show abstract

Extreme semi-supervised learning for multiclass classification

Cited by 10 publications

References 19 publications

GAN‐C: A generative adversarial network with a classifier for effective event prediction

GAN‐C: A generative adversarial network with a classifier for effective event prediction

An Inverse-Free and Scalable Sparse Bayesian Extreme Learning Machine for Classification Problems

Non-iterative and Fast Deep Learning: Multilayer Extreme Learning Machines

Contact Info

Product

Resources

About